1. 07 Aug, 2020 1 commit
    • Chris Jewell's avatar
      Implemented kernel-ised Gibbs sampler · 7adf0699
      Chris Jewell authored
      Changes:
      
      1. Implemented GibbsStep and GibbsKernel classes
      2. Modified mcmc.sample function to use Gibbs sampler
      3. Amended bugs in event_time_mh.py and occult_proposal.py (edge cases where tf.gathers
      were overshooting the bounds of the data stuctures, not apparent on a GPU but raised on
      CPU).
      7adf0699
  2. 06 Aug, 2020 1 commit
  3. 01 Aug, 2020 3 commits
  4. 30 Jul, 2020 6 commits
  5. 24 Jul, 2020 3 commits
  6. 22 Jul, 2020 2 commits
  7. 10 Jul, 2020 1 commit
  8. 09 Jul, 2020 1 commit
  9. 08 Jul, 2020 2 commits
    • Chris Jewell's avatar
      Fix in discrete_markov simulation code · 0b337d47
      Chris Jewell authored
      Bug in discrete_markov.propagate found, introduced after changes for vectorised
      likelihood.
      0b337d47
    • Chris Jewell's avatar
      Added occult inference capability · cad36259
      Chris Jewell authored
      Changes:
      
      1. Added occult Metropolis Hastings update.
      2. Factored out Categorical2 distribution for use by both event time move and occults.
      3. Refactored mcmc.py script for HDF5 output purposes
      4. Apply compression to HDF5 output file.
      cad36259
  10. 05 Jul, 2020 3 commits
  11. 04 Jul, 2020 2 commits
  12. 01 Jul, 2020 1 commit
  13. 29 Jun, 2020 1 commit
  14. 28 Jun, 2020 7 commits
  15. 27 Jun, 2020 2 commits
  16. 26 Jun, 2020 2 commits
    • Chris Jewell's avatar
      Changed storage order of events matrix. · 0291aa34
      Chris Jewell authored
      Previously, the Events matrix expected by model.log_prob was ordered
      [T, M, X] where T is the number of timpoints, M is the number of
      meta-populations and X is the number of transitions.  However, it was
      found more convenient to work with [M, T, X] for the purposes of data
      augmentation.  This meant extra tf.transpose calls.
      
      model.log_prob now expects [M, T, X], with any further batch
      dimensions added as outer dimensions.
      0291aa34
    • Chris Jewell's avatar
      Minor formatting changes to mcmc.py · 8f6ef578
      Chris Jewell authored
      8f6ef578
  17. 25 Jun, 2020 1 commit
  18. 24 Jun, 2020 1 commit
    • Chris Jewell's avatar
      Changes: · e72cfe76
      Chris Jewell authored
      1. Formatting -- black style!
      2. After profiling, implemented a better workaround for the
      tfd.Categorical bug.  Replaced with an inherited Categorical2 class,
      with overloaded log_prob function.
      3. Fixed a  bug in EventTimeProposal where tfd.FiniteDiscrete was
      being used on a non-strictly-increasing outcomes vector.
      4. Increased number of meta-populations to 149 to mirror UK UTLA regions.
      e72cfe76